Novo Nordisk deploys GraphRAG assistant for manufacturing docs on Amazon Bedrock AgentCore
The AWS Machine Learning Blog describes how Novo Nordisk's Manufacturing Technology team built an agentic process-intelligence assistant on Amazon Bedrock AgentCore to answer questions about regulated manufacturing documentation. The system pairs a curated knowledge graph with hybrid dense-vector and BM25 search across Amazon OpenSearch and Amazon Neptune, adds a Bedrock Rerank stage, and clarifies ambiguous questions before retrieving. AWS says the solution helped subject-matter experts finish work that previously took hours or days in minutes.
It is a concrete production deployment of agentic GraphRAG in a regulated pharma environment, where auditability and grounded, cited answers matter more than open-ended extraction.
Novo Nordisk (Novo) is one of the world’s leading global pharmaceutical companies, manufacturing medicines for chronic diseases such as diabetes and obesity, and delivering them to patients across many countries. Behind every product lies a manufacturing network that adheres to strict quality requirements. Every quality-relevant process step must be described, controlled, and validated through formal documentation. Keeping this documentation current and accurate is a core responsibility of the Manufacturing Technology team within the Tablet area, a responsibility that spans a large and diverse portfolio of controlled documents, including standard operating procedures, work instructions, forms, and training materials, across the global organization.
Managing this portfolio presents significant challenges. Document updates are frequent, driven by regulatory changes, process improvements, equipment modifications, and audit findings. Each update demands careful review, structured approval workflows, and timely communication to all affected stakeholders. With thousands of active documents spread across multiple divisions, departments, and product programs, tracking which documents are due for revision, pending approval, or require immediate attention becomes increasingly complex. Much of this oversight currently relies on manual processes and fragmented tracking methods such as spreadsheets or disconnected systems. These methods are time-consuming, error-prone, and difficult to scale. The result is a risk of outdated documentation remaining in circulation, delayed updates, and critical gaps in compliance visibility.
#Novo Nordisk#Amazon Bedrock AgentCore#Amazon Web Services#Amazon Neptune#Amazon OpenSearch#Amazon Bedrock Rerank#Amazon Titan Text Embeddings#Strands Agents SDK